Merge branch 'WIP.x86/asm' into x86/urgent, because the topic is ready

Signed-off-by: Ingo Molnar <mingo@kernel.org>

17 files changed, 378 insertions, 306 deletions

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 64155e310a9f..00eeff94b357 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -165,7 +165,7 @@ config DEBUG_INFO_REDUCED
 
 config DEBUG_INFO_SPLIT
 	bool "Produce split debuginfo in .dwo files"
-	depends on DEBUG_INFO && !FRV
+	depends on DEBUG_INFO
 	help
 	  Generate debug info into separate .dwo files. This significantly
 	  reduces the build directory size for builds with DEBUG_INFO,
@@ -354,10 +354,7 @@ config ARCH_WANT_FRAME_POINTERS
 
 config FRAME_POINTER
 	bool "Compile the kernel with frame pointers"
-	depends on DEBUG_KERNEL && \
-		(CRIS || M68K || FRV || UML || \
-		 SUPERH || BLACKFIN || MN10300 || METAG) || \
-		ARCH_WANT_FRAME_POINTERS
+	depends on DEBUG_KERNEL && (M68K || UML || SUPERH) || ARCH_WANT_FRAME_POINTERS
 	default y if (DEBUG_INFO && UML) || ARCH_WANT_FRAME_POINTERS
 	help
 	  If you say Y here the resulting kernel image will be slightly
@@ -1034,69 +1031,20 @@ config DEBUG_PREEMPT
 
 menu "Lock Debugging (spinlocks, mutexes, etc...)"
 
-config DEBUG_RT_MUTEXES
-	bool "RT Mutex debugging, deadlock detection"
-	depends on DEBUG_KERNEL && RT_MUTEXES
-	help
-	 This allows rt mutex semantics violations and rt mutex related
-	 deadlocks (lockups) to be detected and reported automatically.
-
-config DEBUG_SPINLOCK
-	bool "Spinlock and rw-lock debugging: basic checks"
-	depends on DEBUG_KERNEL
-	select UNINLINE_SPIN_UNLOCK
-	help
-	  Say Y here and build SMP to catch missing spinlock initialization
-	  and certain other kinds of spinlock errors commonly made.  This is
-	  best used in conjunction with the NMI watchdog so that spinlock
-	  deadlocks are also debuggable.
-
-config DEBUG_MUTEXES
-	bool "Mutex debugging: basic checks"
-	depends on DEBUG_KERNEL
-	help
-	 This feature allows mutex semantics violations to be detected and
-	 reported.
-
-config DEBUG_WW_MUTEX_SLOWPATH
-	bool "Wait/wound mutex debugging: Slowpath testing"
-	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
-	select DEBUG_LOCK_ALLOC
-	select DEBUG_SPINLOCK
-	select DEBUG_MUTEXES
-	help
-	 This feature enables slowpath testing for w/w mutex users by
-	 injecting additional -EDEADLK wound/backoff cases. Together with
-	 the full mutex checks enabled with (CONFIG_PROVE_LOCKING) this
-	 will test all possible w/w mutex interface abuse with the
-	 exception of simply not acquiring all the required locks.
-	 Note that this feature can introduce significant overhead, so
-	 it really should not be enabled in a production or distro kernel,
-	 even a debug kernel.  If you are a driver writer, enable it.  If
-	 you are a distro, do not.
-
-config DEBUG_LOCK_ALLOC
-	bool "Lock debugging: detect incorrect freeing of live locks"
-	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
-	select DEBUG_SPINLOCK
-	select DEBUG_MUTEXES
-	select DEBUG_RT_MUTEXES if RT_MUTEXES
-	select LOCKDEP
-	help
-	 This feature will check whether any held lock (spinlock, rwlock,
-	 mutex or rwsem) is incorrectly freed by the kernel, via any of the
-	 memory-freeing routines (kfree(), kmem_cache_free(), free_pages(),
-	 vfree(), etc.), whether a live lock is incorrectly reinitialized via
-	 spin_lock_init()/mutex_init()/etc., or whether there is any lock
-	 held during task exit.
+config LOCK_DEBUGGING_SUPPORT
+	bool
+	depends on TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
+	default y
 
 config PROVE_LOCKING
 	bool "Lock debugging: prove locking correctness"
-	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
+	depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT
 	select LOCKDEP
 	select DEBUG_SPINLOCK
 	select DEBUG_MUTEXES
 	select DEBUG_RT_MUTEXES if RT_MUTEXES
+	select DEBUG_RWSEMS if RWSEM_SPIN_ON_OWNER
+	select DEBUG_WW_MUTEX_SLOWPATH
 	select DEBUG_LOCK_ALLOC
 	select TRACE_IRQFLAGS
 	default n
@@ -1134,20 +1082,9 @@ config PROVE_LOCKING
 
 	 For more details, see Documentation/locking/lockdep-design.txt.
 
-config LOCKDEP
-	bool
-	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
-	select STACKTRACE
-	select FRAME_POINTER if !MIPS && !PPC && !ARM_UNWIND && !S390 && !MICROBLAZE && !ARC && !SCORE && !X86
-	select KALLSYMS
-	select KALLSYMS_ALL
-
-config LOCKDEP_SMALL
-	bool
-
 config LOCK_STAT
 	bool "Lock usage statistics"
-	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
+	depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT
 	select LOCKDEP
 	select DEBUG_SPINLOCK
 	select DEBUG_MUTEXES
@@ -1167,6 +1104,80 @@ config LOCK_STAT
 	 CONFIG_LOCK_STAT defines "contended" and "acquired" lock events.
 	 (CONFIG_LOCKDEP defines "acquire" and "release" events.)
 
+config DEBUG_RT_MUTEXES
+	bool "RT Mutex debugging, deadlock detection"
+	depends on DEBUG_KERNEL && RT_MUTEXES
+	help
+	 This allows rt mutex semantics violations and rt mutex related
+	 deadlocks (lockups) to be detected and reported automatically.
+
+config DEBUG_SPINLOCK
+	bool "Spinlock and rw-lock debugging: basic checks"
+	depends on DEBUG_KERNEL
+	select UNINLINE_SPIN_UNLOCK
+	help
+	  Say Y here and build SMP to catch missing spinlock initialization
+	  and certain other kinds of spinlock errors commonly made.  This is
+	  best used in conjunction with the NMI watchdog so that spinlock
+	  deadlocks are also debuggable.
+
+config DEBUG_MUTEXES
+	bool "Mutex debugging: basic checks"
+	depends on DEBUG_KERNEL
+	help
+	 This feature allows mutex semantics violations to be detected and
+	 reported.
+
+config DEBUG_WW_MUTEX_SLOWPATH
+	bool "Wait/wound mutex debugging: Slowpath testing"
+	depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT
+	select DEBUG_LOCK_ALLOC
+	select DEBUG_SPINLOCK
+	select DEBUG_MUTEXES
+	help
+	 This feature enables slowpath testing for w/w mutex users by
+	 injecting additional -EDEADLK wound/backoff cases. Together with
+	 the full mutex checks enabled with (CONFIG_PROVE_LOCKING) this
+	 will test all possible w/w mutex interface abuse with the
+	 exception of simply not acquiring all the required locks.
+	 Note that this feature can introduce significant overhead, so
+	 it really should not be enabled in a production or distro kernel,
+	 even a debug kernel.  If you are a driver writer, enable it.  If
+	 you are a distro, do not.
+
+config DEBUG_RWSEMS
+	bool "RW Semaphore debugging: basic checks"
+	depends on DEBUG_KERNEL && RWSEM_SPIN_ON_OWNER
+	help
+	  This debugging feature allows mismatched rw semaphore locks and unlocks
+	  to be detected and reported.
+
+config DEBUG_LOCK_ALLOC
+	bool "Lock debugging: detect incorrect freeing of live locks"
+	depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT
+	select DEBUG_SPINLOCK
+	select DEBUG_MUTEXES
+	select DEBUG_RT_MUTEXES if RT_MUTEXES
+	select LOCKDEP
+	help
+	 This feature will check whether any held lock (spinlock, rwlock,
+	 mutex or rwsem) is incorrectly freed by the kernel, via any of the
+	 memory-freeing routines (kfree(), kmem_cache_free(), free_pages(),
+	 vfree(), etc.), whether a live lock is incorrectly reinitialized via
+	 spin_lock_init()/mutex_init()/etc., or whether there is any lock
+	 held during task exit.
+
+config LOCKDEP
+	bool
+	depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT
+	select STACKTRACE
+	select FRAME_POINTER if !MIPS && !PPC && !ARM_UNWIND && !S390 && !MICROBLAZE && !ARC && !X86
+	select KALLSYMS
+	select KALLSYMS_ALL
+
+config LOCKDEP_SMALL
+	bool
+
 config DEBUG_LOCKDEP
 	bool "Lock dependency engine debugging"
 	depends on DEBUG_KERNEL && LOCKDEP
@@ -1571,7 +1582,7 @@ config FAULT_INJECTION_STACKTRACE_FILTER
 	depends on FAULT_INJECTION_DEBUG_FS && STACKTRACE_SUPPORT
 	depends on !X86_64
 	select STACKTRACE
-	select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND && !ARC && !SCORE && !X86
+	select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND && !ARC && !X86
 	help
 	  Provide stacktrace filter for fault-injection capabilities
 
@@ -1969,7 +1980,7 @@ config STRICT_DEVMEM
 	bool "Filter access to /dev/mem"
 	depends on MMU && DEVMEM
 	depends on ARCH_HAS_DEVMEM_IS_ALLOWED
-	default y if TILE || PPC || X86 || ARM64
+	default y if PPC || X86 || ARM64
 	---help---
 	  If this option is disabled, you allow userspace (root) access to all
 	  of memory, including kernel and userspace memory. Accidental
diff --git a/lib/btree.c b/lib/btree.c
index f93a945274af..590facba2c50 100644
--- a/lib/btree.c
+++ b/lib/btree.c
@@ -3,7 +3,7 @@
  *
  * As should be obvious for Linux kernel code, license is GPLv2
  *
- * Copyright (c) 2007-2008 Joern Engel <joern@logfs.org>
+ * Copyright (c) 2007-2008 Joern Engel <joern@purestorage.com>
  * Bits and pieces stolen from Peter Zijlstra's code, which is
  * Copyright 2007, Red Hat Inc. Peter Zijlstra
  * GPLv2
@@ -76,6 +76,8 @@ struct btree_geo btree_geo128 = {
 };
 EXPORT_SYMBOL_GPL(btree_geo128);
 
+#define MAX_KEYLEN	(2 * LONG_PER_U64)
+
 static struct kmem_cache *btree_cachep;
 
 void *btree_alloc(gfp_t gfp_mask, void *pool_data)
@@ -313,7 +315,7 @@ void *btree_get_prev(struct btree_head *head, struct btree_geo *geo,
 {
 	int i, height;
 	unsigned long *node, *oldnode;
-	unsigned long *retry_key = NULL, key[geo->keylen];
+	unsigned long *retry_key = NULL, key[MAX_KEYLEN];
 
 	if (keyzero(geo, __key))
 		return NULL;
@@ -639,8 +641,8 @@ EXPORT_SYMBOL_GPL(btree_remove);
 int btree_merge(struct btree_head *target, struct btree_head *victim,
 		struct btree_geo *geo, gfp_t gfp)
 {
-	unsigned long key[geo->keylen];
-	unsigned long dup[geo->keylen];
+	unsigned long key[MAX_KEYLEN];
+	unsigned long dup[MAX_KEYLEN];
 	void *val;
 	int err;
 
diff --git a/lib/bug.c b/lib/bug.c
index c1b0fad31b10..1077366f496b 100644
--- a/lib/bug.c
+++ b/lib/bug.c
@@ -150,6 +150,8 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs)
 		return BUG_TRAP_TYPE_NONE;
 
 	bug = find_bug(bugaddr);
+	if (!bug)
+		return BUG_TRAP_TYPE_NONE;
 
 	file = NULL;
 	line = 0;
@@ -191,7 +193,7 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs)
 	if (file)
 		pr_crit("kernel BUG at %s:%u!\n", file, line);
 	else
-		pr_crit("Kernel BUG at %p [verbose debug info unavailable]\n",
+		pr_crit("Kernel BUG at %pB [verbose debug info unavailable]\n",
 			(void *)bugaddr);
 
 	return BUG_TRAP_TYPE_BUG;
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 2f5349c6e81a..994be4805cec 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -42,14 +42,18 @@ static struct debug_obj		obj_static_pool[ODEBUG_POOL_SIZE] __initdata;
 static DEFINE_RAW_SPINLOCK(pool_lock);
 
 static HLIST_HEAD(obj_pool);
+static HLIST_HEAD(obj_to_free);
 
 static int			obj_pool_min_free = ODEBUG_POOL_SIZE;
 static int			obj_pool_free = ODEBUG_POOL_SIZE;
 static int			obj_pool_used;
 static int			obj_pool_max_used;
+/* The number of objs on the global free list */
+static int			obj_nr_tofree;
 static struct kmem_cache	*obj_cache;
 
 static int			debug_objects_maxchain __read_mostly;
+static int __maybe_unused	debug_objects_maxchecked __read_mostly;
 static int			debug_objects_fixups __read_mostly;
 static int			debug_objects_warnings __read_mostly;
 static int			debug_objects_enabled __read_mostly
@@ -96,12 +100,32 @@ static const char *obj_states[ODEBUG_STATE_MAX] = {
 static void fill_pool(void)
 {
 	gfp_t gfp = GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN;
-	struct debug_obj *new;
+	struct debug_obj *new, *obj;
 	unsigned long flags;
 
 	if (likely(obj_pool_free >= debug_objects_pool_min_level))
 		return;
 
+	/*
+	 * Reuse objs from the global free list; they will be reinitialized
+	 * when allocating.
+	 */
+	while (obj_nr_tofree && (obj_pool_free < obj_pool_min_free)) {
+		raw_spin_lock_irqsave(&pool_lock, flags);
+		/*
+		 * Recheck with the lock held as the worker thread might have
+		 * won the race and freed the global free list already.
+		 */
+		if (obj_nr_tofree) {
+			obj = hlist_entry(obj_to_free.first, typeof(*obj), node);
+			hlist_del(&obj->node);
+			obj_nr_tofree--;
+			hlist_add_head(&obj->node, &obj_pool);
+			obj_pool_free++;
+		}
+		raw_spin_unlock_irqrestore(&pool_lock, flags);
+	}
+
 	if (unlikely(!obj_cache))
 		return;
 
@@ -177,62 +201,76 @@ alloc_object(void *addr, struct debug_bucket *b, struct debug_obj_descr *descr)
  * workqueue function to free objects.
  *
  * To reduce contention on the global pool_lock, the actual freeing of
- * debug objects will be delayed if the pool_lock is busy. We also free
- * the objects in a batch of 4 for each lock/unlock cycle.
+ * debug objects will be delayed if the pool_lock is busy.
  */
-#define ODEBUG_FREE_BATCH	4
-
 static void free_obj_work(struct work_struct *work)
 {
-	struct debug_obj *objs[ODEBUG_FREE_BATCH];
+	struct hlist_node *tmp;
+	struct debug_obj *obj;
 	unsigned long flags;
-	int i;
+	HLIST_HEAD(tofree);
 
 	if (!raw_spin_trylock_irqsave(&pool_lock, flags))
 		return;
-	while (obj_pool_free >= debug_objects_pool_size + ODEBUG_FREE_BATCH) {
-		for (i = 0; i < ODEBUG_FREE_BATCH; i++) {
-			objs[i] = hlist_entry(obj_pool.first,
-					      typeof(*objs[0]), node);
-			hlist_del(&objs[i]->node);
-		}
 
-		obj_pool_free -= ODEBUG_FREE_BATCH;
-		debug_objects_freed += ODEBUG_FREE_BATCH;
-		/*
-		 * We release pool_lock across kmem_cache_free() to
-		 * avoid contention on pool_lock.
-		 */
-		raw_spin_unlock_irqrestore(&pool_lock, flags);
-		for (i = 0; i < ODEBUG_FREE_BATCH; i++)
-			kmem_cache_free(obj_cache, objs[i]);
-		if (!raw_spin_trylock_irqsave(&pool_lock, flags))
-			return;
+	/*
+	 * The objs on the pool list might be allocated before the work is
+	 * run, so recheck if pool list it full or not, if not fill pool
+	 * list from the global free list
+	 */
+	while (obj_nr_tofree && obj_pool_free < debug_objects_pool_size) {
+		obj = hlist_entry(obj_to_free.first, typeof(*obj), node);
+		hlist_del(&obj->node);
+		hlist_add_head(&obj->node, &obj_pool);
+		obj_pool_free++;
+		obj_nr_tofree--;
+	}
+
+	/*
+	 * Pool list is already full and there are still objs on the free
+	 * list. Move remaining free objs to a temporary list to free the
+	 * memory outside the pool_lock held region.
+	 */
+	if (obj_nr_tofree) {
+		hlist_move_list(&obj_to_free, &tofree);
+		debug_objects_freed += obj_nr_tofree;
+		obj_nr_tofree = 0;
 	}
 	raw_spin_unlock_irqrestore(&pool_lock, flags);
+
+	hlist_for_each_entry_safe(obj, tmp, &tofree, node) {
+		hlist_del(&obj->node);
+		kmem_cache_free(obj_cache, obj);
+	}
 }
 
-/*
- * Put the object back into the pool and schedule work to free objects
- * if necessary.
- */
-static void free_object(struct debug_obj *obj)
+static bool __free_object(struct debug_obj *obj)
 {
 	unsigned long flags;
-	int sched = 0;
+	bool work;
 
 	raw_spin_lock_irqsave(&pool_lock, flags);
-	/*
-	 * schedule work when the pool is filled and the cache is
-	 * initialized:
-	 */
-	if (obj_pool_free > debug_objects_pool_size && obj_cache)
-		sched = 1;
-	hlist_add_head(&obj->node, &obj_pool);
-	obj_pool_free++;
+	work = (obj_pool_free > debug_objects_pool_size) && obj_cache;
 	obj_pool_used--;
+
+	if (work) {
+		obj_nr_tofree++;
+		hlist_add_head(&obj->node, &obj_to_free);
+	} else {
+		obj_pool_free++;
+		hlist_add_head(&obj->node, &obj_pool);
+	}
 	raw_spin_unlock_irqrestore(&pool_lock, flags);
-	if (sched)
+	return work;
+}
+
+/*
+ * Put the object back into the pool and schedule work to free objects
+ * if necessary.
+ */
+static void free_object(struct debug_obj *obj)
+{
+	if (__free_object(obj))
 		schedule_work(&debug_obj_work);
 }
 
@@ -714,13 +752,13 @@ EXPORT_SYMBOL_GPL(debug_object_active_state);
 static void __debug_check_no_obj_freed(const void *address, unsigned long size)
 {
 	unsigned long flags, oaddr, saddr, eaddr, paddr, chunks;
-	struct hlist_node *tmp;
-	HLIST_HEAD(freelist);
 	struct debug_obj_descr *descr;
 	enum debug_obj_state state;
 	struct debug_bucket *db;
+	struct hlist_node *tmp;
 	struct debug_obj *obj;
-	int cnt;
+	int cnt, objs_checked = 0;
+	bool work = false;
 
 	saddr = (unsigned long) address;
 	eaddr = saddr + size;
@@ -751,21 +789,24 @@ repeat:
 				goto repeat;
 			default:
 				hlist_del(&obj->node);
-				hlist_add_head(&obj->node, &freelist);
+				work |= __free_object(obj);
 				break;
 			}
 		}
 		raw_spin_unlock_irqrestore(&db->lock, flags);
 
-		/* Now free them */
-		hlist_for_each_entry_safe(obj, tmp, &freelist, node) {
-			hlist_del(&obj->node);
-			free_object(obj);
-		}
-
 		if (cnt > debug_objects_maxchain)
 			debug_objects_maxchain = cnt;
+
+		objs_checked += cnt;
 	}
+
+	if (objs_checked > debug_objects_maxchecked)
+		debug_objects_maxchecked = objs_checked;
+
+	/* Schedule work to actually kmem_cache_free() objects */
+	if (work)
+		schedule_work(&debug_obj_work);
 }
 
 void debug_check_no_obj_freed(const void *address, unsigned long size)
@@ -780,12 +821,14 @@ void debug_check_no_obj_freed(const void *address, unsigned long size)
 static int debug_stats_show(struct seq_file *m, void *v)
 {
 	seq_printf(m, "max_chain     :%d\n", debug_objects_maxchain);
+	seq_printf(m, "max_checked   :%d\n", debug_objects_maxchecked);
 	seq_printf(m, "warnings      :%d\n", debug_objects_warnings);
 	seq_printf(m, "fixups        :%d\n", debug_objects_fixups);
 	seq_printf(m, "pool_free     :%d\n", obj_pool_free);
 	seq_printf(m, "pool_min_free :%d\n", obj_pool_min_free);
 	seq_printf(m, "pool_used     :%d\n", obj_pool_used);
 	seq_printf(m, "pool_max_used :%d\n", obj_pool_max_used);
+	seq_printf(m, "on_free_list  :%d\n", obj_nr_tofree);
 	seq_printf(m, "objs_allocated:%d\n", debug_objects_allocated);
 	seq_printf(m, "objs_freed    :%d\n", debug_objects_freed);
 	return 0;
diff --git a/lib/dma-direct.c b/lib/dma-direct.c
index c9e8e21cb334..c0bba30fef0a 100644
--- a/lib/dma-direct.c
+++ b/lib/dma-direct.c
@@ -9,6 +9,7 @@
 #include <linux/scatterlist.h>
 #include <linux/dma-contiguous.h>
 #include <linux/pfn.h>
+#include <linux/set_memory.h>
 
 #define DIRECT_MAPPING_ERROR		0
 
@@ -20,6 +21,14 @@
 #define ARCH_ZONE_DMA_BITS 24
 #endif
 
+/*
+ * For AMD SEV all DMA must be to unencrypted addresses.
+ */
+static inline bool force_dma_unencrypted(void)
+{
+	return sev_active();
+}
+
 static bool
 check_addr(struct device *dev, dma_addr_t dma_addr, size_t size,
 		const char *caller)
@@ -37,7 +46,9 @@ check_addr(struct device *dev, dma_addr_t dma_addr, size_t size,
 
 static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
 {
-	return phys_to_dma(dev, phys) + size - 1 <= dev->coherent_dma_mask;
+	dma_addr_t addr = force_dma_unencrypted() ?
+		__phys_to_dma(dev, phys) : phys_to_dma(dev, phys);
+	return addr + size - 1 <= dev->coherent_dma_mask;
 }
 
 void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
@@ -46,6 +57,10 @@ void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	int page_order = get_order(size);
 	struct page *page = NULL;
+	void *ret;
+
+	/* we always manually zero the memory once we are done: */
+	gfp &= ~__GFP_ZERO;
 
 	/* GFP_DMA32 and GFP_DMA are no ops without the corresponding zones: */
 	if (dev->coherent_dma_mask <= DMA_BIT_MASK(ARCH_ZONE_DMA_BITS))
@@ -78,10 +93,15 @@ again:
 
 	if (!page)
 		return NULL;
-
-	*dma_handle = phys_to_dma(dev, page_to_phys(page));
-	memset(page_address(page), 0, size);
-	return page_address(page);
+	ret = page_address(page);
+	if (force_dma_unencrypted()) {
+		set_memory_decrypted((unsigned long)ret, 1 << page_order);
+		*dma_handle = __phys_to_dma(dev, page_to_phys(page));
+	} else {
+		*dma_handle = phys_to_dma(dev, page_to_phys(page));
+	}
+	memset(ret, 0, size);
+	return ret;
 }
 
 /*
@@ -92,9 +112,12 @@ void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t dma_addr, unsigned long attrs)
 {
 	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned int page_order = get_order(size);
 
+	if (force_dma_unencrypted())
+		set_memory_encrypted((unsigned long)cpu_addr, 1 << page_order);
 	if (!dma_release_from_contiguous(dev, virt_to_page(cpu_addr), count))
-		free_pages((unsigned long)cpu_addr, get_order(size));
+		free_pages((unsigned long)cpu_addr, page_order);
 }
 
 static dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
diff --git a/lib/ioremap.c b/lib/ioremap.c
index b808a390e4c3..54e5bbaa3200 100644
--- a/lib/ioremap.c
+++ b/lib/ioremap.c
@@ -91,7 +91,8 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr,
 
 		if (ioremap_pmd_enabled() &&
 		    ((next - addr) == PMD_SIZE) &&
-		    IS_ALIGNED(phys_addr + addr, PMD_SIZE)) {
+		    IS_ALIGNED(phys_addr + addr, PMD_SIZE) &&
+		    pmd_free_pte_page(pmd)) {
 			if (pmd_set_huge(pmd, phys_addr + addr, prot))
 				continue;
 		}
@@ -117,7 +118,8 @@ static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr,
 
 		if (ioremap_pud_enabled() &&
 		    ((next - addr) == PUD_SIZE) &&
-		    IS_ALIGNED(phys_addr + addr, PUD_SIZE)) {
+		    IS_ALIGNED(phys_addr + addr, PUD_SIZE) &&
+		    pud_free_pmd_page(pud)) {
 			if (pud_set_huge(pud, phys_addr + addr, prot))
 				continue;
 		}
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index 30e7dd88148b..9f96fa7bc000 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -322,6 +322,8 @@ EXPORT_SYMBOL_GPL(percpu_ref_switch_to_percpu);
  * This function normally doesn't block and can be called from any context
  * but it may block if @confirm_kill is specified and @ref is in the
  * process of switching to atomic mode by percpu_ref_switch_to_atomic().
+ *
+ * There are no implied RCU grace periods between kill and release.
  */
 void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 				 percpu_ref_func_t *confirm_kill)
diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile
index 4add700ddfe3..44d6b46df051 100644
--- a/lib/raid6/Makefile
+++ b/lib/raid6/Makefile
@@ -7,7 +7,6 @@ raid6_pq-y	+= algos.o recov.o tables.o int1.o int2.o int4.o \
 raid6_pq-$(CONFIG_X86) += recov_ssse3.o recov_avx2.o mmx.o sse1.o sse2.o avx2.o avx512.o recov_avx512.o
 raid6_pq-$(CONFIG_ALTIVEC) += altivec1.o altivec2.o altivec4.o altivec8.o
 raid6_pq-$(CONFIG_KERNEL_MODE_NEON) += neon.o neon1.o neon2.o neon4.o neon8.o recov_neon.o recov_neon_inner.o
-raid6_pq-$(CONFIG_TILEGX) += tilegx8.o
 raid6_pq-$(CONFIG_S390) += s390vx8.o recov_s390xc.o
 
 hostprogs-y	+= mktables
@@ -115,11 +114,6 @@ $(obj)/neon8.c:   UNROLL := 8
 $(obj)/neon8.c:   $(src)/neon.uc $(src)/unroll.awk FORCE
 	$(call if_changed,unroll)
 
-targets += tilegx8.c
-$(obj)/tilegx8.c:   UNROLL := 8
-$(obj)/tilegx8.c:   $(src)/tilegx.uc $(src)/unroll.awk FORCE
-	$(call if_changed,unroll)
-
 targets += s390vx8.c
 $(obj)/s390vx8.c:   UNROLL := 8
 $(obj)/s390vx8.c:   $(src)/s390vx.uc $(src)/unroll.awk FORCE
diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c
index 476994723258..c65aa80d67ed 100644
--- a/lib/raid6/algos.c
+++ b/lib/raid6/algos.c
@@ -75,9 +75,6 @@ const struct raid6_calls * const raid6_algos[] = {
 	&raid6_altivec4,
 	&raid6_altivec8,
 #endif
-#if defined(CONFIG_TILEGX)
-	&raid6_tilegx8,
-#endif
 #if defined(CONFIG_S390)
 	&raid6_s390vx8,
 #endif
diff --git a/lib/raid6/test/Makefile b/lib/raid6/test/Makefile
index be1010bdc435..fabc477b1417 100644
--- a/lib/raid6/test/Makefile
+++ b/lib/raid6/test/Makefile
@@ -51,9 +51,6 @@ else
                 OBJS += altivec1.o altivec2.o altivec4.o altivec8.o
         endif
 endif
-ifeq ($(ARCH),tilegx)
-OBJS += tilegx8.o
-endif
 
 .c.o:
 	$(CC) $(CFLAGS) -c -o $@ $<
@@ -116,15 +113,11 @@ int16.c: int.uc ../unroll.awk
 int32.c: int.uc ../unroll.awk
 	$(AWK) ../unroll.awk -vN=32 < int.uc > $@
 
-tilegx8.c: tilegx.uc ../unroll.awk
-	$(AWK) ../unroll.awk -vN=8 < tilegx.uc > $@
-
 tables.c: mktables
 	./mktables > tables.c
 
 clean:
 	rm -f *.o *.a mktables mktables.c *.uc int*.c altivec*.c neon*.c tables.c raid6test
-	rm -f tilegx*.c
 
 spotless: clean
 	rm -f *~
diff --git a/lib/raid6/tilegx.uc b/lib/raid6/tilegx.uc
deleted file mode 100644
index 2dd291a11264..000000000000
--- a/lib/raid6/tilegx.uc
+++ /dev/null
@@ -1,87 +0,0 @@
-/* -*- linux-c -*- ------------------------------------------------------- *
- *
- *   Copyright 2002 H. Peter Anvin - All Rights Reserved
- *   Copyright 2012 Tilera Corporation - All Rights Reserved
- *
- *   This program is free software; you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation, Inc., 53 Temple Place Ste 330,
- *   Boston MA 02111-1307, USA; either version 2 of the License, or
- *   (at your option) any later version; incorporated herein by reference.
- *
- * ----------------------------------------------------------------------- */
-
-/*
- * tilegx$#.c
- *
- * $#-way unrolled TILE-Gx SIMD for RAID-6 math.
- *
- * This file is postprocessed using unroll.awk.
- *
- */
-
-#include <linux/raid/pq.h>
-
-/* Create 8 byte copies of constant byte */
-# define NBYTES(x) (__insn_v1addi(0, x))
-# define NSIZE  8
-
-/*
- * The SHLBYTE() operation shifts each byte left by 1, *not*
- * rolling over into the next byte
- */
-static inline __attribute_const__ u64 SHLBYTE(u64 v)
-{
-	/* Vector One Byte Shift Left Immediate. */
-	return __insn_v1shli(v, 1);
-}
-
-/*
- * The MASK() operation returns 0xFF in any byte for which the high
- * bit is 1, 0x00 for any byte for which the high bit is 0.
- */
-static inline __attribute_const__ u64 MASK(u64 v)
-{
-	/* Vector One Byte Shift Right Signed Immediate. */
-	return __insn_v1shrsi(v, 7);
-}
-
-
-void raid6_tilegx$#_gen_syndrome(int disks, size_t bytes, void **ptrs)
-{
-	u8 **dptr = (u8 **)ptrs;
-	u64 *p, *q;
-	int d, z, z0;
-
-	u64 wd$$, wq$$, wp$$, w1$$, w2$$;
-	u64 x1d = NBYTES(0x1d);
-	u64 * z0ptr;
-
-	z0 = disks - 3;			/* Highest data disk */
-	p = (u64 *)dptr[z0+1];	/* XOR parity */
-	q = (u64 *)dptr[z0+2];	/* RS syndrome */
-
-	z0ptr = (u64 *)&dptr[z0][0];
-	for ( d = 0 ; d < bytes ; d += NSIZE*$# ) {
-		wq$$ = wp$$ = *z0ptr++;
-		for ( z = z0-1 ; z >= 0 ; z-- ) {
-			wd$$ = *(u64 *)&dptr[z][d+$$*NSIZE];
-			wp$$ = wp$$ ^ wd$$;
-			w2$$ = MASK(wq$$);
-			w1$$ = SHLBYTE(wq$$);
-			w2$$ = w2$$ & x1d;
-			w1$$ = w1$$ ^ w2$$;
-			wq$$ = w1$$ ^ wd$$;
-		}
-		*p++ = wp$$;
-		*q++ = wq$$;
-	}
-}
-
-const struct raid6_calls raid6_tilegx$# = {
-	raid6_tilegx$#_gen_syndrome,
-	NULL,			/* XOR not yet implemented */
-	NULL,
-	"tilegx$#",
-	0
-};
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 3825c30aaa36..47de025b6245 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -506,8 +506,10 @@ static void *rhashtable_lookup_one(struct rhashtable *ht,
 		if (!key ||
 		    (ht->p.obj_cmpfn ?
 		     ht->p.obj_cmpfn(&arg, rht_obj(ht, head)) :
-		     rhashtable_compare(&arg, rht_obj(ht, head))))
+		     rhashtable_compare(&arg, rht_obj(ht, head)))) {
+			pprev = &head->next;
 			continue;
+		}
 
 		if (!ht->rhlist)
 			return rht_obj(ht, head);
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index c67b06261160..32aacd0d56a8 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -31,6 +31,7 @@
 #include <linux/gfp.h>
 #include <linux/scatterlist.h>
 #include <linux/mem_encrypt.h>
+#include <linux/set_memory.h>
 
 #include <asm/io.h>
 #include <asm/dma.h>
@@ -156,22 +157,6 @@ unsigned long swiotlb_size_or_default(void)
 	return size ? size : (IO_TLB_DEFAULT_SIZE);
 }
 
-void __weak swiotlb_set_mem_attributes(void *vaddr, unsigned long size) { }
-
-/* For swiotlb, clear memory encryption mask from dma addresses */
-static dma_addr_t swiotlb_phys_to_dma(struct device *hwdev,
-				      phys_addr_t address)
-{
-	return __sme_clr(phys_to_dma(hwdev, address));
-}
-
-/* Note that this doesn't work with highmem page */
-static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev,
-				      volatile void *address)
-{
-	return phys_to_dma(hwdev, virt_to_phys(address));
-}
-
 static bool no_iotlb_memory;
 
 void swiotlb_print_info(void)
@@ -209,12 +194,12 @@ void __init swiotlb_update_mem_attributes(void)
 
 	vaddr = phys_to_virt(io_tlb_start);
 	bytes = PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT);
-	swiotlb_set_mem_attributes(vaddr, bytes);
+	set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT);
 	memset(vaddr, 0, bytes);
 
 	vaddr = phys_to_virt(io_tlb_overflow_buffer);
 	bytes = PAGE_ALIGN(io_tlb_overflow);
-	swiotlb_set_mem_attributes(vaddr, bytes);
+	set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT);
 	memset(vaddr, 0, bytes);
 }
 
@@ -355,7 +340,7 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
 	io_tlb_start = virt_to_phys(tlb);
 	io_tlb_end = io_tlb_start + bytes;
 
-	swiotlb_set_mem_attributes(tlb, bytes);
+	set_memory_decrypted((unsigned long)tlb, bytes >> PAGE_SHIFT);
 	memset(tlb, 0, bytes);
 
 	/*
@@ -366,7 +351,8 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
 	if (!v_overflow_buffer)
 		goto cleanup2;
 
-	swiotlb_set_mem_attributes(v_overflow_buffer, io_tlb_overflow);
+	set_memory_decrypted((unsigned long)v_overflow_buffer,
+			io_tlb_overflow >> PAGE_SHIFT);
 	memset(v_overflow_buffer, 0, io_tlb_overflow);
 	io_tlb_overflow_buffer = virt_to_phys(v_overflow_buffer);
 
@@ -622,7 +608,7 @@ map_single(struct device *hwdev, phys_addr_t phys, size_t size,
 		return SWIOTLB_MAP_ERROR;
 	}
 
-	start_dma_addr = swiotlb_phys_to_dma(hwdev, io_tlb_start);
+	start_dma_addr = __phys_to_dma(hwdev, io_tlb_start);
 	return swiotlb_tbl_map_single(hwdev, start_dma_addr, phys, size,
 				      dir, attrs);
 }
@@ -706,6 +692,7 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr,
 	}
 }
 
+#ifdef CONFIG_DMA_DIRECT_OPS
 static inline bool dma_coherent_ok(struct device *dev, dma_addr_t addr,
 		size_t size)
 {
@@ -726,12 +713,12 @@ swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		goto out_warn;
 
 	phys_addr = swiotlb_tbl_map_single(dev,
-			swiotlb_phys_to_dma(dev, io_tlb_start),
+			__phys_to_dma(dev, io_tlb_start),
 			0, size, DMA_FROM_DEVICE, 0);
 	if (phys_addr == SWIOTLB_MAP_ERROR)
 		goto out_warn;
 
-	*dma_handle = swiotlb_phys_to_dma(dev, phys_addr);
+	*dma_handle = __phys_to_dma(dev, phys_addr);
 	if (dma_coherent_ok(dev, *dma_handle, size))
 		goto out_unmap;
 
@@ -759,28 +746,6 @@ out_warn:
 	return NULL;
 }
 
-void *
-swiotlb_alloc_coherent(struct device *hwdev, size_t size,
-		       dma_addr_t *dma_handle, gfp_t flags)
-{
-	int order = get_order(size);
-	unsigned long attrs = (flags & __GFP_NOWARN) ? DMA_ATTR_NO_WARN : 0;
-	void *ret;
-
-	ret = (void *)__get_free_pages(flags, order);
-	if (ret) {
-		*dma_handle = swiotlb_virt_to_bus(hwdev, ret);
-		if (dma_coherent_ok(hwdev, *dma_handle, size)) {
-			memset(ret, 0, size);
-			return ret;
-		}
-		free_pages((unsigned long)ret, order);
-	}
-
-	return swiotlb_alloc_buffer(hwdev, size, dma_handle, attrs);
-}
-EXPORT_SYMBOL(swiotlb_alloc_coherent);
-
 static bool swiotlb_free_buffer(struct device *dev, size_t size,
 		dma_addr_t dma_addr)
 {
@@ -799,15 +764,7 @@ static bool swiotlb_free_buffer(struct device *dev, size_t size,
 				 DMA_ATTR_SKIP_CPU_SYNC);
 	return true;
 }
-
-void
-swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
-		      dma_addr_t dev_addr)
-{
-	if (!swiotlb_free_buffer(hwdev, size, dev_addr))
-		free_pages((unsigned long)vaddr, get_order(size));
-}
-EXPORT_SYMBOL(swiotlb_free_coherent);
+#endif
 
 static void
 swiotlb_full(struct device *dev, size_t size, enum dma_data_direction dir,
@@ -867,10 +824,10 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
 	map = map_single(dev, phys, size, dir, attrs);
 	if (map == SWIOTLB_MAP_ERROR) {
 		swiotlb_full(dev, size, dir, 1);
-		return swiotlb_phys_to_dma(dev, io_tlb_overflow_buffer);
+		return __phys_to_dma(dev, io_tlb_overflow_buffer);
 	}
 
-	dev_addr = swiotlb_phys_to_dma(dev, map);
+	dev_addr = __phys_to_dma(dev, map);
 
 	/* Ensure that the address returned is DMA'ble */
 	if (dma_capable(dev, dev_addr, size))
@@ -879,7 +836,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
 	attrs |= DMA_ATTR_SKIP_CPU_SYNC;
 	swiotlb_tbl_unmap_single(dev, map, size, dir, attrs);
 
-	return swiotlb_phys_to_dma(dev, io_tlb_overflow_buffer);
+	return __phys_to_dma(dev, io_tlb_overflow_buffer);
 }
 
 /*
@@ -1009,7 +966,7 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
 				sg_dma_len(sgl) = 0;
 				return 0;
 			}
-			sg->dma_address = swiotlb_phys_to_dma(hwdev, map);
+			sg->dma_address = __phys_to_dma(hwdev, map);
 		} else
 			sg->dma_address = dev_addr;
 		sg_dma_len(sg) = sg->length;
@@ -1073,7 +1030,7 @@ swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
 int
 swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
 {
-	return (dma_addr == swiotlb_phys_to_dma(hwdev, io_tlb_overflow_buffer));
+	return (dma_addr == __phys_to_dma(hwdev, io_tlb_overflow_buffer));
 }
 
 /*
@@ -1085,7 +1042,7 @@ swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
 int
 swiotlb_dma_supported(struct device *hwdev, u64 mask)
 {
-	return swiotlb_phys_to_dma(hwdev, io_tlb_end - 1) <= mask;
+	return __phys_to_dma(hwdev, io_tlb_end - 1) <= mask;
 }
 
 #ifdef CONFIG_DMA_DIRECT_OPS
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 2efb213716fa..3e9335493fe4 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -5467,7 +5467,7 @@ static struct bpf_test tests[] = {
 	{
 		"BPF_MAXINSNS: Jump, gap, jump, ...",
 		{ },
-#ifdef CONFIG_BPF_JIT_ALWAYS_ON
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_X86)
 		CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL,
 #else
 		CLASSIC | FLAG_NO_DATA,
diff --git a/lib/test_kmod.c b/lib/test_kmod.c
index e372b97eee13..0e5b7a61460b 100644
--- a/lib/test_kmod.c
+++ b/lib/test_kmod.c
@@ -1141,7 +1141,7 @@ static struct kmod_test_device *register_test_dev_kmod(void)
 	mutex_lock(&reg_dev_mutex);
 
 	/* int should suffice for number of devices, test for wrap */
-	if (unlikely(num_test_devs + 1) < 0) {
+	if (num_test_devs + 1 == INT_MAX) {
 		pr_err("reached limit of number of test devices\n");
 		goto out;
 	}
diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c
index 76d3667fdea2..f4000c137dbe 100644
--- a/lib/test_rhashtable.c
+++ b/lib/test_rhashtable.c
@@ -79,6 +79,21 @@ struct thread_data {
 	struct test_obj *objs;
 };
 
+static u32 my_hashfn(const void *data, u32 len, u32 seed)
+{
+	const struct test_obj_rhl *obj = data;
+
+	return (obj->value.id % 10) << RHT_HASH_RESERVED_SPACE;
+}
+
+static int my_cmpfn(struct rhashtable_compare_arg *arg, const void *obj)
+{
+	const struct test_obj_rhl *test_obj = obj;
+	const struct test_obj_val *val = arg->key;
+
+	return test_obj->value.id - val->id;
+}
+
 static struct rhashtable_params test_rht_params = {
 	.head_offset = offsetof(struct test_obj, node),
 	.key_offset = offsetof(struct test_obj, value),
@@ -87,6 +102,17 @@ static struct rhashtable_params test_rht_params = {
 	.nulls_base = (3U << RHT_BASE_SHIFT),
 };
 
+static struct rhashtable_params test_rht_params_dup = {
+	.head_offset = offsetof(struct test_obj_rhl, list_node),
+	.key_offset = offsetof(struct test_obj_rhl, value),
+	.key_len = sizeof(struct test_obj_val),
+	.hashfn = jhash,
+	.obj_hashfn = my_hashfn,
+	.obj_cmpfn = my_cmpfn,
+	.nelem_hint = 128,
+	.automatic_shrinking = false,
+};
+
 static struct semaphore prestart_sem;
 static struct semaphore startup_sem = __SEMAPHORE_INITIALIZER(startup_sem, 0);
 
@@ -465,6 +491,112 @@ static int __init test_rhashtable_max(struct test_obj *array,
 	return err;
 }
 
+static unsigned int __init print_ht(struct rhltable *rhlt)
+{
+	struct rhashtable *ht;
+	const struct bucket_table *tbl;
+	char buff[512] = "";
+	unsigned int i, cnt = 0;
+
+	ht = &rhlt->ht;
+	tbl = rht_dereference(ht->tbl, ht);
+	for (i = 0; i < tbl->size; i++) {
+		struct rhash_head *pos, *next;
+		struct test_obj_rhl *p;
+
+		pos = rht_dereference(tbl->buckets[i], ht);
+		next = !rht_is_a_nulls(pos) ? rht_dereference(pos->next, ht) : NULL;
+
+		if (!rht_is_a_nulls(pos)) {
+			sprintf(buff, "%s\nbucket[%d] -> ", buff, i);
+		}
+
+		while (!rht_is_a_nulls(pos)) {
+			struct rhlist_head *list = container_of(pos, struct rhlist_head, rhead);
+			sprintf(buff, "%s[[", buff);
+			do {
+				pos = &list->rhead;
+				list = rht_dereference(list->next, ht);
+				p = rht_obj(ht, pos);
+
+				sprintf(buff, "%s val %d (tid=%d)%s", buff, p->value.id, p->value.tid,
+					list? ", " : " ");
+				cnt++;
+			} while (list);
+
+			pos = next,
+			next = !rht_is_a_nulls(pos) ?
+				rht_dereference(pos->next, ht) : NULL;
+
+			sprintf(buff, "%s]]%s", buff, !rht_is_a_nulls(pos) ? " -> " : "");
+		}
+	}
+	printk(KERN_ERR "\n---- ht: ----%s\n-------------\n", buff);
+
+	return cnt;
+}
+
+static int __init test_insert_dup(struct test_obj_rhl *rhl_test_objects,
+				  int cnt, bool slow)
+{
+	struct rhltable rhlt;
+	unsigned int i, ret;
+	const char *key;
+	int err = 0;
+
+	err = rhltable_init(&rhlt, &test_rht_params_dup);
+	if (WARN_ON(err))
+		return err;
+
+	for (i = 0; i < cnt; i++) {
+		rhl_test_objects[i].value.tid = i;
+		key = rht_obj(&rhlt.ht, &rhl_test_objects[i].list_node.rhead);
+		key += test_rht_params_dup.key_offset;
+
+		if (slow) {
+			err = PTR_ERR(rhashtable_insert_slow(&rhlt.ht, key,
+							     &rhl_test_objects[i].list_node.rhead));
+			if (err == -EAGAIN)
+				err = 0;
+		} else
+			err = rhltable_insert(&rhlt,
+					      &rhl_test_objects[i].list_node,
+					      test_rht_params_dup);
+		if (WARN(err, "error %d on element %d/%d (%s)\n", err, i, cnt, slow? "slow" : "fast"))
+			goto skip_print;
+	}
+
+	ret = print_ht(&rhlt);
+	WARN(ret != cnt, "missing rhltable elements (%d != %d, %s)\n", ret, cnt, slow? "slow" : "fast");
+
+skip_print:
+	rhltable_destroy(&rhlt);
+
+	return 0;
+}
+
+static int __init test_insert_duplicates_run(void)
+{
+	struct test_obj_rhl rhl_test_objects[3] = {};
+
+	pr_info("test inserting duplicates\n");
+
+	/* two different values that map to same bucket */
+	rhl_test_objects[0].value.id = 1;
+	rhl_test_objects[1].value.id = 21;
+
+	/* and another duplicate with same as [0] value
+	 * which will be second on the bucket list */
+	rhl_test_objects[2].value.id = rhl_test_objects[0].value.id;
+
+	test_insert_dup(rhl_test_objects, 2, false);
+	test_insert_dup(rhl_test_objects, 3, false);
+	test_insert_dup(rhl_test_objects, 2, true);
+	test_insert_dup(rhl_test_objects, 3, true);
+
+	return 0;
+}
+
 static int thread_lookup_test(struct thread_data *tdata)
 {
 	unsigned int entries = tdata->entries;
@@ -613,6 +745,8 @@ static int __init test_rht_init(void)
 	do_div(total_time, runs);
 	pr_info("Average test time: %llu\n", total_time);
 
+	test_insert_duplicates_run();
+
 	if (!tcount)
 		return 0;
 
diff --git a/lib/test_user_copy.c b/lib/test_user_copy.c
index 4621db801b23..e161f0498f42 100644
--- a/lib/test_user_copy.c
+++ b/lib/test_user_copy.c
@@ -31,11 +31,8 @@
  * their capability at compile-time, we just have to opt-out certain archs.
  */
 #if BITS_PER_LONG == 64 || (!(defined(CONFIG_ARM) && !defined(MMU)) && \
-			    !defined(CONFIG_BLACKFIN) &&	\
-			    !defined(CONFIG_M32R) &&		\
 			    !defined(CONFIG_M68K) &&		\
 			    !defined(CONFIG_MICROBLAZE) &&	\
-			    !defined(CONFIG_MN10300) &&		\
 			    !defined(CONFIG_NIOS2) &&		\
 			    !defined(CONFIG_PPC32) &&		\
 			    !defined(CONFIG_SUPERH))